{"created":"2025-01-19T01:36:51.512668+00:00","updated":"2025-01-19T09:39:47.006389+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00234944","sets":["1164:2735:11468:11669"]},"path":["11669"],"owner":"44499","recid":"234944","title":["誤り訂正を組み込んだ新たなホップフィールドニューラルネットワークモデルの提案"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-06-13"},"_buckets":{"deposit":"f8359fb6-5692-463d-9d79-15379b14a03d"},"_deposit":{"id":"234944","pid":{"type":"depid","value":"234944","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"誤り訂正を組み込んだ新たなホップフィールドニューラルネットワークモデルの提案","author_link":["641231","641232","641230"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"誤り訂正を組み込んだ新たなホップフィールドニューラルネットワークモデルの提案"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"数理モデル化と問題解決2","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2024-06-13","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"現在，横浜国立大学大学院大学院環境情報学府"},{"subitem_text_value":"現在，横浜国立大学大学院大学院環境情報学府"},{"subitem_text_value":"現在，横浜国立大学大学院総合学術高等研究院"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Presently with Graduate School of Environment and Information Sciences, Yokohama National University","subitem_text_language":"en"},{"subitem_text_value":"Presently with Graduate School of Environment and Information Sciences, Yokohama National University","subitem_text_language":"en"},{"subitem_text_value":"Presently with Institute of Multidisciplinary Sciences, Yokohama National University","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/234944/files/IPSJ-MPS24148057.pdf","label":"IPSJ-MPS24148057.pdf"},"date":[{"dateType":"Available","dateValue":"2026-06-13"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-MPS24148057.pdf","filesize":[{"value":"1.1 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"17"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"c17e63bd-7c6c-4668-9afc-e39fe4411de9","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"中西, 流我"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"荒井, 敏"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"長尾, 智晴"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10505667","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8833","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"ホップフィールドニューラルネットワークは相互結合型のニューラルネットワークであり，任意のビットパターンを記憶し，それらのパターンを想起することができる．しかし，記憶可能なパターン数は最大でノード数の 14% 程度であることが知られており，記憶容量が少ないという問題がある．また，想起の際に極小値に陥ってしまうという問題もある．この問題を解決するべく，ホップフィールドニューラルネットワークをもとにした，記憶パターンが指数関数的に増える誤り訂正モデルも提案されているが，任意のパターンを記憶することができず，記憶できるパターンに制限がかかるという問題がある．そこで本研究では，この記憶パターンが指数関数的に増える誤り訂正モデルと，Hebb 則における連想記憶を組み合わせることで，新たなホップフィールドニューラルネットワークモデルを提案する．このモデルは任意のパターンを記憶することができ，相互結合型ニューラルネットワークの特徴である追加学習も容易に行うことができる．そのうえで，ホップフィールドニューラルネットワークよりも記憶容量が大きく，計算コストも小さいことを，実験やモデルの性質などによって示した．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告数理モデル化と問題解決（MPS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2024-06-13","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"57","bibliographicVolumeNumber":"2024-MPS-148"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":234944,"links":{}}